查看文章

Traditionally, the field of recommender systems has evaluated the fruits of its labor using metrics of algorithmic accuracy and precision (see Chap. 8 for an overview of recommender systems evaluation practices). Netflix organized a million-dollar contest for just this goal of improving the accuracy of its movie recommendation algorithm [7]. In recent years, however, researchers have come to realize that the goal of a recommender system extends well beyond accurate predictions; its primary real-world purpose is to provide personalized help in discovering relevant content or items [72].

This has caused two important changes in the field. The first change was incited by McNee et al.[83] who argued that “being accurate is not enough” and that one should instead “study recommenders from a user-centric perspective to make them not only accurate and helpful, but also a pleasure to use”(p. 1101). McNee et al. suggest …